Global Patent Index - EP 4040342 A4

EP 4040342 A4 20230802 - DEEP NEUTRAL NETWORK STRUCTURE LEARNING AND SIMPLIFYING METHOD

Title (en)

DEEP NEUTRAL NETWORK STRUCTURE LEARNING AND SIMPLIFYING METHOD

Title (de)

VERFAHREN ZUM LERNEN DER STRUKTUR EINES TIEFEN NEUTRALEN NETZES UND ZUR VEREINFACHUNG

Title (fr)

PROCÉDÉ D'APPRENTISSAGE ET DE SIMPLIFICATION DE STRUCTURE DE RÉSEAU NEURONAL PROFOND

Publication

EP 4040342 A4 20230802 (EN)

Application

EP 20871182 A 20200929

Priority

  • KR 20190121906 A 20191002
  • KR 20200043231 A 20200409
  • KR 20200075692 A 20200622
  • KR 20200126288 A 20200928
  • KR 2020013304 W 20200929

Abstract (en)

[origin: EP4040342A1] The present invention relates to a method for structure learning and model compression for a deep neural network. The method for structure learning and model compression for a deep neural network according to an embodiment of the present invention includes (a) generating a parameter for a neural network model, (b) generating an objective function corresponding to the neural network model on the basis of the parameter, and (c) performing training on the parameter and performing model learning on the basis of the objective function and learning data.

IPC 8 full level

G06N 3/084 (2023.01); G06N 3/0495 (2023.01); G06N 3/082 (2023.01); G06N 3/0985 (2023.01); G06N 3/063 (2023.01)

CPC (source: CN EP US)

G06N 3/04 (2013.01 - US); G06N 3/045 (2023.01 - CN); G06N 3/0495 (2023.01 - EP); G06N 3/08 (2013.01 - US); G06N 3/082 (2013.01 - CN EP); G06N 3/0985 (2023.01 - EP); G06N 3/0464 (2023.01 - EP); G06N 3/048 (2023.01 - EP); G06N 3/063 (2013.01 - EP); G06N 3/084 (2013.01 - EP); G06N 3/09 (2023.01 - EP)

Citation (search report)

  • [XI] SANGKUG LYM ET AL: "PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 27 January 2019 (2019-01-27), XP081546883, DOI: 10.1145/3295500.3356156
  • [XI] RAMCHALAM KINATTINKARA RAMAKRISHNAN ET AL: "Differentiable Mask Pruning for Neural Networks", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 10 September 2019 (2019-09-10), XP081476193
  • See references of WO 2021066504A1

Designated contracting state (EPC)

AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DOCDB simple family (publication)

EP 4040342 A1 20220810; EP 4040342 A4 20230802; CN 114503122 A 20220513; US 2022343162 A1 20221027; WO 2021066504 A1 20210408

DOCDB simple family (application)

EP 20871182 A 20200929; CN 202080069687 A 20200929; KR 2020013304 W 20200929; US 202017760650 A 20200929